python用yfinance抓取数据

def history(self, period="1mo", interval="1d",
            start=None, end=None, prepost=False, actions=True,
            auto_adjust=True, back_adjust=False,
            proxy=None, rounding=False, tz=None, timeout=None, **kwargs):
    """
    :Parameters:
        period : str
            Valid periods: 1d,5d,1mo,3mo,6mo,1y,2y,5y,10y,ytd,max
            Either Use period parameter or use start and end
        interval : str
            Valid intervals: 1m,2m,5m,15m,30m,60m,90m,1h,1d,5d,1wk,1mo,3mo
            Intraday data cannot extend last 60 days
        start: str
            Download start date string (YYYY-MM-DD) or _datetime.
            Default is 1900-01-01
        end: str
            Download end date string (YYYY-MM-DD) or _datetime.
            Default is now
        prepost : bool
            Include Pre and Post market data in results?
            Default is False
        auto_adjust: bool
            Adjust all OHLC automatically? Default is True
        back_adjust: bool
            Back-adjusted data to mimic true historical prices
        proxy: str
            Optional. Proxy server URL scheme. Default is None
        rounding: bool
            Round values to 2 decimal places?
            Optional. Default is False = precision suggested by Yahoo!
        tz: str
            Optional timezone locale for dates.
            (default data is returned as non-localized dates)
        timeout: None or float
            If not None stops waiting for a response after given number of
            seconds. (Can also be a fraction of a second e.g. 0.01)
            Default is None.
        **kwargs: dict
            debug: bool
                Optional. If passed as False, will suppress
                error message printing to console.
    """

data = goog.history(interval='1m', start='2022-01-03', end='2022-01-10')
data.head()

def download(tickers, start=None, end=None, actions=False, threads=True,
             group_by='column', auto_adjust=False, back_adjust=False,
             progress=True, period="max", show_errors=True, interval="1d", prepost=False,
             proxy=None, rounding=False, timeout=None, **kwargs):
    """Download yahoo tickers
    :Parameters:
        tickers : str, list
            List of tickers to download
        period : str
            Valid periods: 1d,5d,1mo,3mo,6mo,1y,2y,5y,10y,ytd,max
            Either Use period parameter or use start and end
        interval : str
            Valid intervals: 1m,2m,5m,15m,30m,60m,90m,1h,1d,5d,1wk,1mo,3mo
            Intraday data cannot extend last 60 days
        start: str
            Download start date string (YYYY-MM-DD) or _datetime.
            Default is 1900-01-01
        end: str
            Download end date string (YYYY-MM-DD) or _datetime.
            Default is now
        group_by : str
            Group by 'ticker' or 'column' (default)
        prepost : bool
            Include Pre and Post market data in results?
            Default is False
        auto_adjust: bool
            Adjust all OHLC automatically? Default is False
        actions: bool
            Download dividend + stock splits data. Default is False
        threads: bool / int
            How many threads to use for mass downloading. Default is True
        proxy: str
            Optional. Proxy server URL scheme. Default is None
        rounding: bool
            Optional. Round values to 2 decimal places?
        show_errors: bool
            Optional. Doesn't print errors if True
        timeout: None or float
            If not None stops waiting for a response after given number of
            seconds. (Can also be a fraction of a second e.g. 0.01)
    """

data = yf.download(['GOOG','META'], period='1mo')
data.head()

data = yf.download(['GOOG','META'], start='2021-12-10', end='2021-12-30', group_by='ticker')
data.head()

dhr = yf.Ticker('DHR')
info = dhr.info
info.keys()

info['sector']
'Healthcare'

dhr.earnings

dhr.get_financials()

pnl = dhr.financials
bs = dhr.balancesheet
cf = dhr.cashflow
fs = pd.concat([pnl,bs,cf])
print(fs)

fs.T

tickers = ['FB','AMZN','NFLX','GOOG']
tickers

tickers = [yf.Ticker(ticker) for ticker in fang]

[yfinance.Ticker object <FB>,
 yfinance.Ticker object <AMZN>,
 yfinance.Ticker object <NFLX>,
 yfinance.Ticker object <GOOG>]

dfs = [] # list for each ticker's dataframe
for ticker in tickers:
    # get each financial statement
    pnl = ticker.financials
    bs = ticker.balancesheet
    cf = ticker.cashflow

    # concatenate into one dataframe
    fs = pd.concat([pnl, bs, cf])

    # make dataframe format nicer
    # Swap dates and columns
    data = fs.T
    # reset index (date) into a column
    data = data.reset_index()
    # Rename old index from '' to Date
    data.columns = ['Date', *data.columns[1:]]
    # Add ticker to dataframe
    data['Ticker'] = ticker.ticker
    dfs.append(data)
data.iloc[:,:3]# for display purposes

parser = pd.io.parsers.base_parser.ParserBase({'usecols': None})

for df in dfs:
     df.columns = parser._maybe_dedup_names(df.columns)
df = pd.concat(dfs, ignore_index=True)
df = df.set_index(['Ticker','Date'])
df.iloc[:,:5] # for display purposes

calls = options.calls
calls

puts = options.puts
puts

aapl.insitutional_holders